Overview for recommendations
See how Hortonworks and Cloudera is using the latest in Apache Hive, Spark, Druid and Impala in data warehousing, analytics and recommendations.
This talk is about how Sailthru leverages diverse features about users and items to build a recommendation system that will be used by several media and ecommerce companies. In particular, learn how they make use of Spark SQL to extract user and item level features, (b) How they run Spark code in production and best practices for building effective Spark application, (c) How they make use GBMs to use diverse features and various algorithms to make final recommendations for each user, and (d) How they make use of Spark MLlib to make recommendations for millions of users by scoring over ten thousand items per user.
Learn how Experticity leverages spark extensively for their big data pipelines, machine learning capabilities, steaming and much more.
Sujit Mathew and Yew Yap Goh from PayPal discuss:
- How they use data to boost engagement for PayPal products with their consumers
- Collaborative filtering and how they scale models on Hadoop cluster
- How they design content models and hybrid models
- How they use property graphs and graph modeling
- Visualizing our data for stakeholders
- How they take our models to production